ABSTRACT
This study adopts recurrent neural networks (RNN) with its Long Short-Term Memory (LSTM) architecture to predict the ambient temperature (TA). The prediction is based on meteorological data retrieved from IoT stations, these IoT stations consist of different components such as sensors to capture the temperature, humidity and some gases in the air, and send them to the basic station with LoRa protocol. We formulate the TA prediction problem as a time series regression problem. LSTM is a particular type of recurrent neural network, which has a strong ability to model the temporal relationship of time series data and can well manage the problem of long-term dependency. The proposed network architecture consists of two types of hidden layers: LSTM layer and full connected dense layer. The LSTM layer is used to model the time series relationship. The fully connected layer is used to map the output of the LSTM layer to a final prediction. To confirm the effectiveness of the proposed model, we perform tests on data collected by our own IoT system on Tangier. In addition, we show all the results in a web interface.
- Augustin, A., Yi, J., Clausen, T. and Townsley, W.M. 2016. A Study of LoRa: Long Range & Low Power Networks for the Internet of Things. Sensors. 16, 9 (Sep. 2016), 1466.Google ScholarCross Ref
- Gamboa, J.C.B. 2017. Deep Learning for Time-Series Analysis. arXiv:1701.01887 {cs}. (Jan. 2017).Google Scholar
- Goldoni, E., Prando, L., Vizziello, A., Savazzi, P. and Gamba, P. 2019. Experimental data set analysis of RSSI-based indoor and outdoor localization in LoRa networks. Internet Technology Letters. 2, 1 (Jan. 2019), e75.Google ScholarCross Ref
- Ha, J.-H., Lee, Y.H. and Kim, Y.-H. 2016. Forecasting the Precipitation of the Next Day Using Deep Learning. Journal of Korean Institute of Intelligent Systems. 26, 2 (2016), 93--98.Google ScholarCross Ref
- Hochreiter, S. and Schmidhuber, J. 1997. Long Short-Term Memory. Neural Computation. 9, 8 (Nov. 1997), 1735--1780. Google ScholarDigital Library
- Ordóñez, F.J. and Roggen, D. 2016. Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors (Basel, Switzerland). 16, 1 (Jan. 2016).Google Scholar
- Petrić, T., Goessens, M., Nuaymi, L., Toutain, L. and Pelov, A. 2016. Measurements, performance and analysis of LoRa FABIAN, a real-world implementation of LPWAN. 2016 IEEE 27th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC) (Sep. 2016), 1--7.Google ScholarDigital Library
- Ray, P.P. 2016. A survey on Internet of Things architectures. Journal of King Saud University - Computer and Information Sciences. (Oct. 2016).Google Scholar
- Sanubari, A.R., Kusuma, P.D. and Setianingsih, C. 2018. Flood Modelling and Prediction Using Artificial Neural Network. 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS) (Nov. 2018), 227--233.Google Scholar
- Singh, B. 2019. The Internet of Things: A Vision for Smart World. Advances in Signal Processing and Communication (2019), 165--172.Google Scholar
- Xie, X., Wu, D., Liu, S. and Li, R. 2017. IoT Data Analytics Using Deep Learning. arXiv:1708.03854 {cs}. (Aug. 2017).Google Scholar
- Yang, J. and Fang, B. 2011. Security model and key technologies for the Internet of things. The Journal of China Universities of Posts and Telecommunications. 18, (Dec. 2011), 109--112.Google Scholar
- Zhang, Q., Wang, H., Dong, J., Zhong, G. and Sun, X. 2017. Prediction of Sea Surface Temperature Using Long Short-Term Memory. IEEE Geoscience and Remote Sensing Letters. 14, 10 (Oct. 2017), 1745--1749.Google ScholarCross Ref
- Zhao, J., Deng, F., Cai, Y. and Chen, J. 2019. Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. Chemosphere. 220, (Apr. 2019), 486--492.Google Scholar
Recommendations
A multiple time series-based recurrent neural network for short-term load forecasting
Electricity, an indispensable resource in daily life and industrial production, is hard to store, so accurate short-term load forecasting (STLF) plays a vital role in resource allocation, capital budgeting of power companies, energy deployment and ...
Prediction of air pollution using LSTM-based recurrent neural networks
This paper proposes a system that predicts the pollution level at some hour at a place. It also infers about the various parameters associated with the increasing pollution across the globe, its ill effects and the future scenario of the same. An air ...
Deep long short-term memory based model for agricultural price forecasting
AbstractAgricultural price forecasting is one of the research hotspots in time series forecasting due to its unique characteristics. In this paper, we developed a deep long short-term memory (DLSTM) based model for the accurate forecasting of a ...
Comments